FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness

Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Ziqiang Cao, Sujian Li, Hua Wu


Abstract
Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem.In this paper, we study the faithfulness of existing systems from a new perspective of factual robustness which is the ability to correctly generate factual information over adversarial unfaithful information.We first measure a model’sfactual robustness by its success rate to defend against adversarial attacks when generating factual information.The factual robustness analysis on a wide range of current systems shows its good consistency with human judgments on faithfulness.Inspired by these findings, we propose to improve the faithfulness of a model by enhancing its factual robustness.Specifically, we propose a novel training strategy, namely FRSUM, which teaches the model to defend against both explicit adversarial samples and implicit factual adversarial perturbations.Extensive automatic and human evaluation results show that FRSUM consistently improves the faithfulness of various Seq2Seq models, such as T5, BART.
Anthology ID:
2022.findings-emnlp.267
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3640–3654
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.267
DOI:
10.18653/v1/2022.findings-emnlp.267
Bibkey:
Cite (ACL):
Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Ziqiang Cao, Sujian Li, and Hua Wu. 2022. FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3640–3654, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness (Wu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.267.pdf